ms-mamba: Multi-scale mamba for time-series forecasting

Date

2026-06-01

Author

Karadag, Yusuf Meric
Talaz, Ismail
Gürsel Dino, İpek
KALKAN, SİNAN

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

1574
views

0
downloads

Cite This

The problem of time-series forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale, which may be sub-optimal for many tasks where information changes over multiple time scales. In this paper, we introduce a novel architecture called Multi-scale Mamba (ms-Mamba) to address this gap. ms-Mamba incorporates multiple temporal scales by using multiple Mamba blocks with different sampling rates (Δs). Our experiments on many benchmarks demonstrate that ms-Mamba outperforms state-of-the-art approaches, including the recently proposed Transformer-based and Mamba-based models. For example, on the Solar-Energy dataset, ms-Mamba outperforms its closest competitor S-Mamba (0.229 vs. 0.240 in terms of mean-squared error) while using fewer parameters (3.53M vs. 4.77M), less memory (13.46MB vs. 18.18MB), and less operations (14.93G vs. 20.53G MACs), averaged across four forecast lengths. Codes and models will be made available.

Subject Keywords

Mamba, Multi-scale Mamba, Time-series forecasting

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105032512125&origin=inward
https://hdl.handle.net/11511/118944

Collections

Department of Architecture, Article